Created
August 28, 2010 20:04
-
-
Save anonymous/555510 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
from BeautifulSoup import BeautifulSoup | |
import csv, os, sys, urllib2 | |
from bsoupxpath import Path | |
import chardet | |
import html5lib | |
from html5lib import treebuilders | |
DATAPATH = '/vol/grants/data/' | |
RAWDATAPATH = DATAPATH + 'raw/' | |
CSVDATAPATH = DATAPATH + 'csv/' | |
def extract_simple_html_table(url, xpath, csvfilename, encoding=None, skip_top=1): | |
bc = open(csvfilename, 'w') | |
bcw = csv.writer(bc, dialect=csv.excel) | |
tp = Path(xpath) | |
f = urllib2.urlopen(url) | |
data = f.read() | |
# print chardet.detect(data) | |
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("beautifulsoup")) | |
if encoding: | |
soup = parser.parse(data, encoding=encoding) | |
# soup = BeautifulSoup(data, fromEncoding=encoding) | |
else: | |
soup = parser.parse(data) | |
# print soup | |
objs = tp.apply(soup) | |
if not objs or len(objs) == 0: | |
return | |
table = objs[0] | |
rows = table.findAll('tr') | |
print len(rows) | |
for row in rows[skip_top:]: | |
rdata = [] | |
cols = row.findAll('td') | |
for col in cols: | |
text = u''.join([e for e in col.recursiveChildGenerator() if isinstance(e,unicode)]).replace(u'\n', u' ').strip() | |
rdata.append(text.encode('utf8')) | |
empty = True | |
for c in rdata: | |
if len(c) > 0: | |
empty = False | |
break | |
if empty: continue | |
bcw.writerow(rdata) | |
bc.close() | |
def run_all(): | |
extract_simple_html_table('http://www.gosclub.ru/images/content/tablk.html', xpath='//table', csvfilename="data/csv/gosclub_2009.csv", encoding='KOI8-R', skip_top=6) | |
extract_simple_html_table('http://nbfond.ru/konkurs-grantov/granty-2009/spisok-pobeditelej/', xpath="//table[@border='1']", csvfilename='data/csv/nbfond_2009.csv', encoding="utf8", skip_top=1) | |
extract_simple_html_table('http://nbfond.ru/konkurs-grantov/granty-2008/spisok-pobeditelej/', xpath="//div[@id='content']/table", csvfilename='data/csv/nbfond_2008.csv', encoding="utf8", skip_top=1) | |
extract_simple_html_table('http://nbfond.ru/konkurs-grantov/granty-2007/spisok-pobeditelej/', xpath="//div[@id='content']/table", csvfilename='data/csv/nbfond_2007.csv', encoding="utf8", skip_top=1) | |
extract_simple_html_table('http://www.soprotivlenie.org/?id=124', xpath="//div[@class='kr-plan']/table", csvfilename='data/csv/soprotivlenie_2009.csv', encoding='windows-1251', skip_top=1) | |
extract_simple_html_table('http://www.inpgo.ru/495/496/579/', xpath="//table[@class='border']", csvfilename="data/csv/inpgo_2009.csv", encoding='windows-1251', skip_top=1) | |
extract_simple_html_table('http://www.inop.ru/page143/page298/page84/page576/', xpath="//table[@width='823']", csvfilename='data/csv/inop_2009.csv', encoding='windows-1251', skip_top=1) | |
extract_simple_html_table('http://www.inop.ru/page143/page530/page382/', xpath="//table[@width='648']", csvfilename='data/csv/inop_2008.csv', encoding='windows-1251', skip_top=1) | |
extract_simple_html_table('http://www.inop.ru/page143/page531/page505/', xpath="//table[@align='center']", csvfilename='data/csv/inop_2007.csv', encoding='windows-1251', skip_top=1) | |
extract_simple_html_table('http://znaniesvet.com/index.php?option=com_content&task=view&id=221', xpath="//table[@class='MsoNormalTable']", csvfilename='data/csv/znanie_2008.csv', encoding='windows-1251', skip_top=1) | |
extract_simple_html_table('http://znaniesvet.com/content/view/135/80/', xpath="//table[@width='957']", csvfilename='data/csv/znanie_2007.csv', encoding='windows-1251', skip_top=1) | |
if __name__ == "__main__": | |
run_all() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment